> ## Documentation Index
> Fetch the complete documentation index at: https://docs.traceport.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Dashboard

> Real-time analytics and metrics for your AI operations.

The **Dashboard** is your primary entry point into Traceport, giving you immediate situational awareness over your AI integration's health and usage.

<Frame>
  <video autoPlay loop muted playsInline src="https://mintcdn.com/traceport/ZXBNThc7kv_3RvjA/images/dashboard.mp4?fit=max&auto=format&n=ZXBNThc7kv_3RvjA&q=85&s=6500431e37ed58eb6b39b9cf1d9b5798" className="w-full rounded-lg" data-path="images/dashboard.mp4" />
</Frame>

## Core Metrics

The dashboard displays real-time charts and metrics across your entire AI operations:

| Metric             | Description                                                       |
| ------------------ | ----------------------------------------------------------------- |
| **Request Volume** | Total inbound requests across all endpoints and providers         |
| **Costs**          | Aggregated financial spend across all connected LLM providers     |
| **Cache Hits**     | Semantic caching performance — tracks cache hit rates and savings |
| **Token Usage**    | Aggregated prompt (input) and completion (output) token totals    |
| **Latency**        | Request latency distribution and trends over time                 |

## API Keys Overview

The dashboard also shows an at-a-glance status of your active API keys, including usage statistics per key. This helps you quickly identify which keys are driving the most traffic.

<Tip>
  Use the time range selector at the top of the dashboard to filter metrics by specific periods — last hour, last day, last week, or custom ranges.
</Tip>